Research on ontology-based situation understanding and decision-making approach for MASS

Abstract

Aiming at the problems of miscellaneous navigation safety information and the difficulty of multi-source heterogeneous information fusion, a novel ontology-based collision avoidance decision making method is proposed in this paper. first of all, the structured ontology model of navigation situation is built on the basis of analysing the hierarchy and interactivity of various scene elements in driving scene and constructing the semantic model of entity class and binary attribute of scene elements, implement effective modelling of navigation scenarios. Secondly, the knowledge base of collision avoidance decision and online reasoning system are constructed based on the semantic expression of typical scene elements to realize the efficient utilization of navigation prior knowledge. Finally, the simulation experiment is carried out for the typical ship encounter scenarios in open water. The results show that the ontology method can effectively improve the cognition ability of Maritime Autonomous Surface Ships (MASS), and meet the requirements for real-time, safety and rationality of collision avoidance decision.